// SCAN REPORT

DevToolkit MCP Server

32 tools. 6 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 29 Jun 2026

6 can modify or destroy data

26 read-only

32 tools total

Community server · catalogue entry verified 29/06/2026

How to control DevToolkit MCP Server ↓

TOOL MAP

What DevToolkit MCP Server exposes to your agents

Read (26) Write / Execute (5) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous DevToolkit MCP Server tools

Destructive · High delete_file The tool deletes files or directories, which is an irreversible operation that destroys data. Execute · High http_request This tool can trigger arbitrary external HTTP operations including state-changing methods (POST, PUT, PATCH, DELETE) against any endpoint with custom headers and body. Execute · High run_background This tool executes arbitrary shell commands and external processes that persist beyond the tool's execution. Execute · Critical run_command Shell command execution is a classic Execute category tool because its effects depend entirely on the arguments provided (which command to run).

6 of DevToolkit MCP Server's 32 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control DevToolkit MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and DevToolkit MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_file": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "download_file": {
    "limits": [
      {
        "counter": "download_file_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_complexity": {
    "limits": [
      {
        "counter": "analyze_complexity_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register DevToolkit MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON DEVTOOLKIT →

Instant setup, no code required.

FULL CATALOGUE

All 32 DevToolkit MCP Server tools

DESTRUCTIVE 1 tools

Destructive delete_file Delete a file or directory. Always asks for user confirmation first.

EXECUTE 3 tools

Execute http_request Make an HTTP request. Supports GET, POST, PUT, PATCH, DELETE with custom headers and body. Execute run_background Start a long-running process (dev servers, watchers) in the background. Captures output for a few seconds then Execute run_command Execute a shell command safely. Validated against an allowlist of safe tools.

WRITE 2 tools

Write download_file Download a file from a URL and save it to a local path. Write write_file Write content to a file, creating it if needed. Asks for confirmation if file already exists.

READ 26 tools

Read analyze_complexity Analyze code complexity: functions, classes, nesting depth, cyclomatic complexity. Read check_command_status Check if a background command (started with run_background) has finished. Returns running=true/false, exit_cod Read check_port Check if a TCP port is open/listening on localhost. Use after run_background to confirm a dev server started. Read check_url_status Check the HTTP status and response time of one or more URLs. Read count_lines Count total, blank, comment, and code lines in a file or directory. Read detect_language Detect the programming language of a file. Read fetch_json Fetch JSON from a URL and return it formatted. Supports dot-path extraction. Read find_duplicates Find duplicate or near-duplicate code blocks across files. Read find_todos Find all TODO, FIXME, HACK, NOTE, and XXX comments in files, then AI-prioritizes them by urgency. Read get_disk_usage Get disk usage for a directory or the whole system. Read get_env Read environment variables. Sensitive values are automatically masked. Read get_file_info Get metadata for a file: size, timestamps, permissions. Read get_imports Extract all import/require statements from a source file. Read get_network_info Get network interfaces and their IP addresses. Read get_system_info Get detailed system information: OS, CPU, memory, architecture, hostname. Read git_blame Show what revision and author last modified each line of a file. Read git_branches List all local and remote branches. Read git_diff Show diff between commits, branches, or working tree. Read git_log Get the commit history for a repository. Read git_show_commit Show details and diff for a specific commit. Read git_status Show the working tree status of a git repository. Read list_directory List files and directories at a given path with metadata. Read list_processes List running processes with their PID, name, and resource usage. Read read_file Read the contents of a file. Supports optional line range. Read read_process_output Read the latest buffered output from a background process started with run_background. Read search_in_files Search for a text pattern across files using glob patterns.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about DevToolkit MCP Server

Can an AI agent delete data through the DevToolkit MCP Server MCP server? +

Yes. The DevToolkit MCP Server server exposes 1 destructive tools including delete_file. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through DevToolkit MCP Server? +

The DevToolkit MCP Server server has 2 write tools including download_file, write_file. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach DevToolkit MCP Server.

How many tools does the DevToolkit MCP Server MCP server expose? +

32 tools across 4 categories: Destructive, Execute, Read, Write. 26 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on DevToolkit MCP Server? +

Register the DevToolkit MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every DevToolkit MCP Server tool call.

Deterministic rules across all 32 DevToolkit MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DEVTOOLKIT →

Instant setup, no code required.

32 DevToolkit MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.